#Ruchi Moondra
#Assignment: World Happiness Analysis
#Loading the data
worldh <- read.csv("C:/Users/Ruchi/Desktop/Ruchi/Rutgers/Multivariate/Dataset/WH_2017.csv")
#Loading packages required for the analysis
library(plyr)
library(plotly)
## Loading required package: ggplot2
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following objects are masked from 'package:plyr':
##
## arrange, mutate, rename, summarise
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:plyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyverse)
## -- Attaching packages -------------------------------------------------------------------------------- tidyverse 1.2.1 --
## v tibble 2.0.1 v purrr 0.3.0
## v tidyr 0.8.2 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.3.0
## -- Conflicts ----------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::arrange() masks plotly::arrange(), plyr::arrange()
## x purrr::compact() masks plyr::compact()
## x dplyr::count() masks plyr::count()
## x dplyr::failwith() masks plyr::failwith()
## x dplyr::filter() masks plotly::filter(), stats::filter()
## x dplyr::id() masks plyr::id()
## x dplyr::lag() masks stats::lag()
## x dplyr::mutate() masks plotly::mutate(), plyr::mutate()
## x dplyr::rename() masks plotly::rename(), plyr::rename()
## x dplyr::summarise() masks plotly::summarise(), plyr::summarise()
## x dplyr::summarize() masks plyr::summarize()
library(lubridate)
##
## Attaching package: 'lubridate'
## The following object is masked from 'package:plyr':
##
## here
## The following object is masked from 'package:base':
##
## date
library(caTools)
library(ggplot2)
library(ggthemes)
library(reshape2)
##
## Attaching package: 'reshape2'
## The following object is masked from 'package:tidyr':
##
## smiths
library(data.table)
##
## Attaching package: 'data.table'
## The following objects are masked from 'package:reshape2':
##
## dcast, melt
## The following objects are masked from 'package:lubridate':
##
## hour, isoweek, mday, minute, month, quarter, second, wday,
## week, yday, year
## The following object is masked from 'package:purrr':
##
## transpose
## The following objects are masked from 'package:dplyr':
##
## between, first, last
library(tidyr)
library(corrgram)
##
## Attaching package: 'corrgram'
## The following object is masked from 'package:plyr':
##
## baseball
library(corrplot)
## corrplot 0.84 loaded
library(formattable)
##
## Attaching package: 'formattable'
## The following object is masked from 'package:plotly':
##
## style
library(cowplot)
##
## Attaching package: 'cowplot'
## The following object is masked from 'package:ggthemes':
##
## theme_map
## The following object is masked from 'package:ggplot2':
##
## ggsave
library(ggpubr)
## Loading required package: magrittr
##
## Attaching package: 'magrittr'
## The following object is masked from 'package:purrr':
##
## set_names
## The following object is masked from 'package:tidyr':
##
## extract
##
## Attaching package: 'ggpubr'
## The following object is masked from 'package:cowplot':
##
## get_legend
## The following object is masked from 'package:plyr':
##
## mutate
library(plot3D)
library(latexpdf)
library(car)
## Loading required package: carData
##
## Attaching package: 'car'
## The following object is masked from 'package:purrr':
##
## some
## The following object is masked from 'package:dplyr':
##
## recode
library(FactoMineR)
library(factoextra)
## Welcome! Related Books: `Practical Guide To Cluster Analysis in R` at https://goo.gl/13EFCZ
library(corrplot)
library(mice)
## Loading required package: lattice
##
## Attaching package: 'lattice'
## The following object is masked from 'package:corrgram':
##
## panel.fill
##
## Attaching package: 'mice'
## The following object is masked from 'package:tidyr':
##
## complete
## The following objects are masked from 'package:base':
##
## cbind, rbind
#View the data
View(worldh)
#Displays the first few rows of the dataset
head(worldh)
## Country Happiness.Rank Happiness.Score Whisker.high Whisker.low
## 1 Norway 1 7.537 7.594445 7.479556
## 2 Denmark 2 7.522 7.581728 7.462272
## 3 Iceland 3 7.504 7.622030 7.385970
## 4 Switzerland 4 7.494 7.561772 7.426227
## 5 Finland 5 7.469 7.527542 7.410458
## 6 Netherlands 6 7.377 7.427426 7.326574
## Economy..GDP.per.Capita. Family Health..Life.Expectancy. Freedom
## 1 1.616463 1.533524 0.7966665 0.6354226
## 2 1.482383 1.551122 0.7925655 0.6260067
## 3 1.480633 1.610574 0.8335521 0.6271626
## 4 1.564980 1.516912 0.8581313 0.6200706
## 5 1.443572 1.540247 0.8091577 0.6179509
## 6 1.503945 1.428939 0.8106961 0.5853845
## Generosity Trust..Government.Corruption. Dystopia.Residual
## 1 0.3620122 0.3159638 2.277027
## 2 0.3552805 0.4007701 2.313707
## 3 0.4755402 0.1535266 2.322715
## 4 0.2905493 0.3670073 2.276716
## 5 0.2454828 0.3826115 2.430182
## 6 0.4704898 0.2826618 2.294804
#Display the structure of the attributes
str(worldh)
## 'data.frame': 155 obs. of 12 variables:
## $ Country : Factor w/ 155 levels "Afghanistan",..: 105 38 58 133 45 99 26 100 132 7 ...
## $ Happiness.Rank : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Happiness.Score : num 7.54 7.52 7.5 7.49 7.47 ...
## $ Whisker.high : num 7.59 7.58 7.62 7.56 7.53 ...
## $ Whisker.low : num 7.48 7.46 7.39 7.43 7.41 ...
## $ Economy..GDP.per.Capita. : num 1.62 1.48 1.48 1.56 1.44 ...
## $ Family : num 1.53 1.55 1.61 1.52 1.54 ...
## $ Health..Life.Expectancy. : num 0.797 0.793 0.834 0.858 0.809 ...
## $ Freedom : num 0.635 0.626 0.627 0.62 0.618 ...
## $ Generosity : num 0.362 0.355 0.476 0.291 0.245 ...
## $ Trust..Government.Corruption.: num 0.316 0.401 0.154 0.367 0.383 ...
## $ Dystopia.Residual : num 2.28 2.31 2.32 2.28 2.43 ...
# Adding another column name "Continent"
worldh$Continent <- NA
# Deleting unnecessary columns (Whisker.high and Whisker.low)
worldh <- worldh[, -c(4,5)]
# Changing the name of columns
colnames (worldh) <- c("Country", "Happiness.Rank", "Happiness.Score",
"Economy", "Family", "Life.Expectancy", "Freedom", "Generosity",
"Trust", "Dystopia.Residual", "Continent")
# Adding the values for Continent name in the data.
worldh$Continent[which(worldh$Country %in% c("Israel", "United Arab Emirates", "Singapore", "Thailand", "Taiwan Province of China",
"Qatar", "Saudi Arabia", "Kuwait", "Bahrain", "Malaysia", "Uzbekistan", "Japan",
"South Korea", "Turkmenistan", "Kazakhstan", "Turkey", "Hong Kong S.A.R., China", "Philippines",
"Jordan", "China", "Pakistan", "Indonesia", "Azerbaijan", "Lebanon", "Vietnam",
"Tajikistan", "Bhutan", "Kyrgyzstan", "Nepal", "Mongolia", "Palestinian Territories",
"Iran", "Bangladesh", "Myanmar", "Iraq", "Sri Lanka", "Armenia", "India", "Georgia",
"Cambodia", "Afghanistan", "Yemen", "Syria"))] <- "Asia"
worldh$Continent[which(worldh$Country %in% c("Norway", "Denmark", "Iceland", "Switzerland", "Finland",
"Netherlands", "Sweden", "Austria", "Ireland", "Germany",
"Belgium", "Luxembourg", "United Kingdom", "Czech Republic",
"Malta", "France", "Spain", "Slovakia", "Poland", "Italy",
"Russia", "Lithuania", "Latvia", "Moldova", "Romania",
"Slovenia", "North Cyprus", "Cyprus", "Estonia", "Belarus",
"Serbia", "Hungary", "Croatia", "Kosovo", "Montenegro",
"Greece", "Portugal", "Bosnia and Herzegovina", "Macedonia",
"Bulgaria", "Albania", "Ukraine"))] <- "Europe"
worldh$Continent[which(worldh$Country %in% c("Canada", "Costa Rica", "United States", "Mexico",
"Panama","Trinidad and Tobago", "El Salvador", "Belize", "Guatemala",
"Jamaica", "Nicaragua", "Dominican Republic", "Honduras",
"Haiti"))] <- "North America"
worldh$Continent[which(worldh$Country %in% c("Chile", "Brazil", "Argentina", "Uruguay",
"Colombia", "Ecuador", "Bolivia", "Peru",
"Paraguay", "Venezuela"))] <- "South America"
worldh$Continent[which(worldh$Country %in% c("New Zealand", "Australia"))] <- "Australia"
worldh$Continent[which(is.na(worldh$Continent))] <- "Africa"
# Moving the Continent column at the second position.
worldh <- worldh %>% select(Country,Continent, everything())
str(worldh)
## 'data.frame': 155 obs. of 11 variables:
## $ Country : Factor w/ 155 levels "Afghanistan",..: 105 38 58 133 45 99 26 100 132 7 ...
## $ Continent : chr "Europe" "Europe" "Europe" "Europe" ...
## $ Happiness.Rank : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Happiness.Score : num 7.54 7.52 7.5 7.49 7.47 ...
## $ Economy : num 1.62 1.48 1.48 1.56 1.44 ...
## $ Family : num 1.53 1.55 1.61 1.52 1.54 ...
## $ Life.Expectancy : num 0.797 0.793 0.834 0.858 0.809 ...
## $ Freedom : num 0.635 0.626 0.627 0.62 0.618 ...
## $ Generosity : num 0.362 0.355 0.476 0.291 0.245 ...
## $ Trust : num 0.316 0.401 0.154 0.367 0.383 ...
## $ Dystopia.Residual: num 2.28 2.31 2.32 2.28 2.43 ...
#Converting the Continent values into factorial.
worldh$Continent <- as.factor(worldh$Continent)
# Finding the correlation between numerical columns
Num.cols <- sapply(worldh, is.numeric)
Cor.data <- cor(worldh[, Num.cols])
corrplot(Cor.data, method = 'color')
#Analysis: We can see there is an inverse correlation between "Happiness Rank" and all the other numerical variables. In other words, the lower the happiness rank, the higher the happiness score, and the higher the other seven factors that contribute to happiness. So let's remove the happiness rank, and see the correlation again.
# Create a correlation plot
newdatacor = cor(worldh[c(3:10)])
corrplot(newdatacor, method = "number")
#Analysis: In the above cor plot, Economy, life expectancy, and family play the most significant role in contributing to happiness.
#Trust and generosity have the lowest impact on the happiness score.
#Plotting ScatterPLot
plot_ly(data = worldh,
x=~Economy, y=~Happiness.Score, type = "scatter",
text = ~paste("Country:", Country)) %>%
layout(title = "Happiness and GDP",
xaxis = list(title = "GDP per Capita"),
yaxis = list(title = "Happiness Score"))
## No scatter mode specifed:
## Setting the mode to markers
## Read more about this attribute -> https://plot.ly/r/reference/#scatter-mode
#Analysis: This interactive scatterplot shows that there is a strong positive correlation between GDP and Happiness.
#Let's do multiple Regression
dat <- worldh[c("Happiness.Score","Economy","Generosity")]
head(dat)
## Happiness.Score Economy Generosity
## 1 7.537 1.616463 0.3620122
## 2 7.522 1.482383 0.3552805
## 3 7.504 1.480633 0.4755402
## 4 7.494 1.564980 0.2905493
## 5 7.469 1.443572 0.2454828
## 6 7.377 1.503945 0.4704898
plot(dat)
#It seems like there is a positive correlation between economy and happiness score but this is not true between happiness score
#and generosity.
#3D plot of same
scatter3D(dat$Generosity, dat$Economy, dat$Happiness.Score, phi = 0, bty = "g",
pch = 20, cex = 2, ticktype = "detailed",
main = "Happiness data", xlab = "Generosity",
ylab ="Economy", zlab = "Happiness.Score")
#From the scatter plot we cannot determine that combination of high economy and generosity leads to greater happiness score.
#This is something we have to conclude after analyzing the effect of these 2 taken together.
# Checking the outliers in the dataset using the boxplot.
names(worldh)[4] <- "Happiness_Score"
ggplot(worldh, aes(x=Continent, y= Happiness_Score, colour = Continent)) +
geom_boxplot() +
theme(axis.text.x = element_text(angle = 60, hjust = 1)) +
labs(title = "Happiness Score Boxplot",
x = "Continent",
y = "Happiness Score")
##Checking for normality using shaprio test
qqPlot(worldh$Economy)
## [1] 155 93
shapiro.test(worldh$Economy)
##
## Shapiro-Wilk normality test
##
## data: worldh$Economy
## W = 0.96977, p-value = 0.00175
#p-value is greater than 0.05 implying that the data is not significantly different from normal distribution
qqPlot(worldh$Family)
## [1] 155 152
shapiro.test(worldh$Family)
##
## Shapiro-Wilk normality test
##
## data: worldh$Family
## W = 0.91152, p-value = 4.186e-08
qqPlot(worldh$Life.Expectancy)
## [1] 139 106
shapiro.test(worldh$Life.Expectancy)
##
## Shapiro-Wilk normality test
##
## data: worldh$Life.Expectancy
## W = 0.94602, p-value = 1.135e-05
qqPlot(worldh$Freedom)
## [1] 140 130
shapiro.test(worldh$Freedom)
##
## Shapiro-Wilk normality test
##
## data: worldh$Freedom
## W = 0.95945, p-value = 0.0001673
qqPlot(worldh$Generosity)
## [1] 114 81
shapiro.test(worldh$Generosity)
##
## Shapiro-Wilk normality test
##
## data: worldh$Generosity
## W = 0.95783, p-value = 0.0001184
qqPlot(worldh$Trust)
## [1] 26 151
shapiro.test(worldh$Trust)
##
## Shapiro-Wilk normality test
##
## data: worldh$Trust
## W = 0.83902, p-value = 9.204e-12
#Family,Life expectancy and trust variables are not normally distributed